activity
20112024
most citedGraphACT: Accelerating GCN Training on CPU-FPGA Heterogeneous Platforms

123 citations · 305 across the 26 of their papers we have counts for

collaborators
Showing cs.DCShow all

7 papers · 1 filter

cs.DC20211 cited

Parallel Peeling of Bipartite Networks for Hierarchical Dense Subgraph Discovery

Kartik Lakhotia, Rajgopal Kannan, Viktor Prasanna

Wing and Tip decomposition construct a hierarchy of butterfly-dense edge and vertex induced bipartite subgraphs, respectively. They have applications in several domains including e…

cs.DC20215 cited

A High Throughput Parallel Hash Table on FPGA using XOR-based Memory

Ruizhi Zhang, Sasindu Wijeratne, Yang Yang +2

Hash table is a fundamental data structure for quick search and retrieval of data. It is a key component in complex graph analytics and AI/ML applications. State-of-the-art paralle…

cs.DC202017 cited

DYNAMAP: Dynamic Algorithm Mapping Framework for Low Latency CNN Inference

Yuan Meng, Sanmukh Kuppannagari, Rajgopal Kannan +1

Most of the existing work on FPGA acceleration of Convolutional Neural Network (CNN) focus on employing a single strategy (algorithm, dataflow, etc.) across all the layers. Such an…

cs.DC2020

RECEIPT: REfine CoarsE-grained IndePendent Tasks for Parallel Tip decomposition of Bipartite Graphs

Kartik Lakhotia, Rajgopal Kannan, Viktor Prasanna +1

Tip decomposition is a crucial kernel for mining dense subgraphs in bipartite networks, with applications in spam detection, analysis of affiliation networks etc. It creates a hier…

cs.DC2019123 cited

GraphACT: Accelerating GCN Training on CPU-FPGA Heterogeneous Platforms

Hanqing Zeng, Viktor Prasanna

Graph Convolutional Networks (GCNs) have emerged as the state-of-the-art deep learning model for representation learning on graphs. It is challenging to accelerate training of GCNs…

cs.DC2019

Planting Trees for scalable and efficient Canonical Hub Labeling

Kartik Lakhotia, Qing Dong, Rajgopal Kannan +1

Point-to-Point Shortest Distance (PPSD) query is a crucial primitive in graph database applications. Hub labeling algorithms compute a labeling that converts a PPSD query into a li…